| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8, | |
| "eval_steps": 500, | |
| "global_step": 175, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 7.9200921058654785, | |
| "learning_rate": 4.8e-05, | |
| "loss": 5.7051, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.6645238399505615, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.2689, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.637652397155762, | |
| "learning_rate": 8.83838383838384e-05, | |
| "loss": 0.2192, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.7763524055480957, | |
| "learning_rate": 7.575757575757576e-05, | |
| "loss": 0.1836, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.533644437789917, | |
| "learning_rate": 6.313131313131313e-05, | |
| "loss": 0.1687, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.9909617900848389, | |
| "learning_rate": 5.050505050505051e-05, | |
| "loss": 0.0919, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 2.7650041580200195, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.0918, | |
| "step": 175 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 248, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4019041661178752e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |